Don't worry about mistakes! Glass Segmentation Network via Mistake Correction
This work addresses the challenge of accurately segmenting transparent glass in images, which is important for applications like robotics and augmented reality, but it appears incremental as it builds on existing segmentation methods with a novel correction mechanism.
The paper tackles the problem of transparent glass segmentation by proposing GlassSegNet, which uses an identification stage and a correction stage inspired by human mistake correction, resulting in clear improvements over 34 state-of-the-art methods on three benchmark datasets.
Recall one time when we were in an unfamiliar mall. We might mistakenly think that there exists or does not exist a piece of glass in front of us. Such mistakes will remind us to walk more safely and freely at the same or a similar place next time. To absorb the human mistake correction wisdom, we propose a novel glass segmentation network to detect transparent glass, dubbed GlassSegNet. Motivated by this human behavior, GlassSegNet utilizes two key stages: the identification stage (IS) and the correction stage (CS). The IS is designed to simulate the detection procedure of human recognition for identifying transparent glass by global context and edge information. The CS then progressively refines the coarse prediction by correcting mistake regions based on gained experience. Extensive experiments show clear improvements of our GlassSegNet over thirty-four state-of-the-art methods on three benchmark datasets.